Search Results for author: Guillaume-Alexandre Bilodeau

Found 59 papers, 33 papers with code

CenterDisks: Real-time instance segmentation with disk covering

1 code implementation5 Mar 2024 Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau

In the learning phase, we consider the radius as proportional to a standard deviation in order to compute the error to propagate on a set of two-dimensional Gaussian functions rather than disks.

Real-time Instance Segmentation Semantic Segmentation

Detection of Micromobility Vehicles in Urban Traffic Videos

1 code implementation28 Feb 2024 Khalil Sabri, Célia Djilali, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Wassim Bouachir

Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes.

Object object-detection +1

STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction

1 code implementation11 Dec 2023 Xi Ye, Guillaume-Alexandre Bilodeau

Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents.

Video Prediction

1D-Convolutional transformer for Parkinson disease diagnosis from gait

1 code implementation6 Nov 2023 Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau

Our experimental results show that our approach is effective for detecting the different stages of Parkinson's disease from gait data, with a final accuracy of 88%, outperforming other state-of-the-art AI methods on the Physionet gait dataset.

HCT: Hybrid Convnet-Transformer for Parkinson's disease detection and severity prediction from gait

1 code implementation26 Oct 2023 Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau

Our hybrid architecture exploits the strengths of both Convolutional Neural Networks (ConvNets) and Transformers to accurately detect PD and determine the severity stage.

severity prediction

Automating lichen monitoring in ecological studies using instance segmentation of time-lapse images

no code implementations26 Oct 2023 Safwen Naimi, Olfa Koubaa, Wassim Bouachir, Guillaume-Alexandre Bilodeau, Gregory Jeddore, Patricia Baines, David Correia, Andre Arsenault

These cameras are used by ecologists in Newfoundland and Labrador to subsequently analyze and manually segment the images to determine lichen thalli condition and change.

Instance Segmentation Semantic Segmentation

Real-time instance segmentation with polygons using an Intersection-over-Union loss

1 code implementation9 May 2023 Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau

In this paper, we improve over CenterPoly by enhancing the classical regression L1 loss with a novel region-based loss and a novel order loss, as well as with a new training process for the vertices prediction head.

Real-time Instance Segmentation regression +1

VisiTherS: Visible-thermal infrared stereo disparity estimation of human silhouette

1 code implementation22 Apr 2023 Noreen Anwar, Philippe Duplessis-Guindon, Guillaume-Alexandre Bilodeau, Wassim Bouachir

To address the aforementioned challenges, this paper proposes a novel approach where a high-resolution convolutional neural network is used to better capture relationships between the two spectra.

Disparity Estimation Stereo Disparity Estimation

GUILGET: GUI Layout GEneration with Transformer

1 code implementation18 Apr 2023 Andrey Sobolevsky, Guillaume-Alexandre Bilodeau, Jinghui Cheng, Jin L. C. Guo

Arranging all components inside a GUI layout manually is a time-consuming task.

TopTrack: Tracking Objects By Their Top

1 code implementation12 Apr 2023 Jacob Meilleur, Guillaume-Alexandre Bilodeau

We propose TopTrack, a joint detection-and-tracking method that uses the top of the object as a keypoint for detection instead of the center because it is more often visible.

Multi-Object Tracking Object

Video Prediction by Efficient Transformers

1 code implementation12 Dec 2022 Xi Ye, Guillaume-Alexandre Bilodeau

Video prediction is a challenging computer vision task that has a wide range of applications.

Video Prediction

A unified model for continuous conditional video prediction

1 code implementation11 Oct 2022 Xi Ye, Guillaume-Alexandre Bilodeau

Different conditional video prediction tasks, like video future frame prediction and video frame interpolation, are normally solved by task-related models even though they share many common underlying characteristics.

Video Frame Interpolation Video Prediction

Improving tracking with a tracklet associator

no code implementations22 Apr 2022 Rémi Nahon, Guillaume-Alexandre Bilodeau, Gilles Pesant

In the second phase, we associate the previously constructed tracklets using a Belief Propagation Constraint Programming algorithm, where we propose various constraints that assign scores to each of the tracklets based on multiple characteristics, such as their dynamics or the distance between them in time and space.

Multiple Object Tracking

VPTR: Efficient Transformers for Video Prediction

1 code implementation29 Mar 2022 Xi Ye, Guillaume-Alexandre Bilodeau

Based on this new Transformer block, a fully autoregressive video future frames prediction Transformer is proposed.

Video Prediction

Leveraging Sentiment Analysis Knowledge to Solve Emotion Detection Tasks

no code implementations5 Nov 2021 Maude Nguyen-The, Guillaume-Alexandre Bilodeau, Jan Rockemann

Identifying and understanding underlying sentiment or emotions in text is a key component of multiple natural language processing applications.

Emotion Recognition Sentiment Analysis

PolyTrack: Tracking with Bounding Polygons

1 code implementation2 Nov 2021 Gaspar Faure, Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons.

Multi-Object Tracking Multi-Object Tracking and Segmentation +1

Multi-Object Tracking and Segmentation with a Space-Time Memory Network

no code implementations21 Oct 2021 Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier

We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets.

Instance Segmentation Multi-Object Tracking +10

Vehicle Detection and Tracking From Surveillance Cameras in Urban Scenes

no code implementations25 Sep 2021 Oumayma Messoussi, Felipe Gohring de Magalhaes, Francois Lamarre, Francis Perreault, Ibrahima Sogoba, Guillaume-Alexandre Bilodeau, Gabriela Nicolescu

Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits.

Multi-Object Tracking Object +1

CenterPoly: real-time instance segmentation using bounding polygons

1 code implementation19 Aug 2021 Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier

The models were trained and evaluated on Cityscapes, KITTI and IDD and the results are reported on their public benchmark, which are state-of-the-art at real-time speeds.

Real-time Instance Segmentation Semantic Segmentation

MeNToS: Tracklets Association with a Space-Time Memory Network

no code implementations15 Jul 2021 Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier

We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection.

Instance Segmentation Multi-Object Tracking +7

Multiple Convolutional Features in Siamese Networks for Object Tracking

1 code implementation1 Mar 2021 Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed.

Object Object Tracking

MFST: Multi-Features Siamese Tracker

1 code implementation1 Mar 2021 Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

Based on this advanced feature representation, our algorithm achieves high tracking accuracy, while outperforming several state-of-the-art trackers, including standard Siamese trackers.

Local Anomaly Detection in Videos using Object-Centric Adversarial Learning

no code implementations13 Nov 2020 Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud

We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos.

Anomaly Detection Object

An Empirical Analysis of Visual Features for Multiple Object Tracking in Urban Scenes

1 code implementation15 Oct 2020 Mehdi Miah, Justine Pepin, Nicolas Saunier, Guillaume-Alexandre Bilodeau

Commonly used features are color histograms, histograms of oriented gradients, deep features from convolutional neural networks and re-identification (ReID) features.

Multiple Object Tracking

Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification

no code implementations30 Jul 2020 Yacine Khraimeche, Guillaume-Alexandre Bilodeau, David Steele, Harshad Mahadik

Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation, and adapts the ReID model to an unlabelled target domain by learning disentangled latent representations on the domain.

Disentanglement Domain Adaptive Person Re-Identification +3

Domain Siamese CNNs for Sparse Multispectral Disparity Estimation

no code implementations30 Apr 2020 David-Alexandre Beaupre, Guillaume-Alexandre Bilodeau

Multispectral disparity estimation is a difficult task for many reasons: it has all the same challenges as traditional visible-visible disparity estimation (occlusions, repetitive patterns, textureless surfaces), in addition of having very few common visual information between images (e. g. color information vs. thermal information).

Disparity Estimation

Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study

1 code implementation30 Mar 2020 Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking framework.

Multiple Object Tracking Object

Tracking Road Users using Constraint Programming

no code implementations10 Mar 2020 Alexandre Pineault, Guillaume-Alexandre Bilodeau, Gilles Pesant

Because our focus is on the data association problem, our MOT method only uses simple image features, which are the center position and color of detections for each frame.

Multiple Object Tracking

SpotNet: Self-Attention Multi-Task Network for Object Detection

1 code implementation13 Feb 2020 Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier

We use those segmentation maps inside the network as a self-attention mechanism to weight the feature map used to produce the bounding boxes, decreasing the signal of non-relevant areas.

Instance Segmentation Multi-Task Learning +4

Tracking in Urban Traffic Scenes from Background Subtraction and Object Detection

no code implementations15 May 2019 Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we propose to combine detections from background subtraction and from a multiclass object detector for multiple object tracking (MOT) in urban traffic scenes.

Multiple Object Tracking Object +3

Road User Detection in Videos

1 code implementation28 Mar 2019 Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Pierre Gravel

Two new models, RetinaNet-Double and RetinaNet-Flow, are proposed, based respectively on the concatenation of a target frame with a preceding frame, and the concatenation of the optical flow with the target frame.

object-detection Video Object Detection

Online Mutual Foreground Segmentation for Multispectral Stereo Videos

1 code implementation8 Sep 2018 Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, Robert Bergevin

The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications.

Foreground Segmentation

Multiple Object Tracking in Urban Traffic Scenes with a Multiclass Object Detector

no code implementations6 Sep 2018 Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier, David-Alexandre Beaupré

Multiple object tracking (MOT) in urban traffic aims to produce the trajectories of the different road users that move across the field of view with different directions and speeds and that can have varying appearances and sizes.

General Classification Multiple Object Tracking +2

Road User Abnormal Trajectory Detection using a Deep Autoencoder

1 code implementation25 Aug 2018 Pankaj Raj Roy, Guillaume-Alexandre Bilodeau

In this paper, we focus on the development of a method that detects abnormal trajectories of road users at traffic intersections.

BIG-bench Machine Learning Outlier Detection

Multi-Branch Siamese Networks with Online Selection for Object Tracking

no code implementations22 Aug 2018 Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

In this paper, we propose a robust object tracking algorithm based on a branch selection mechanism to choose the most efficient object representations from multi-branch siamese networks.

Object Object Tracking

Improving Multiple Object Tracking with Optical Flow and Edge Preprocessing

no code implementations29 Jan 2018 David-Alexandre Beaupré, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we present a new method for detecting road users in an urban environment which leads to an improvement in multiple object tracking.

Multiple Object Tracking object-detection +2

From Superpixel to Human Shape Modelling for Carried Object Detection

no code implementations10 Jan 2018 Farnoosh Ghadiri, Robert Bergevin, Guillaume-Alexandre Bilodeau

We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales.

Object object-detection +2

Domain-Specific Face Synthesis for Video Face Recognition from a Single Sample Per Person

1 code implementation6 Jan 2018 Fania Mokhayeri, Eric Granger, Guillaume-Alexandre Bilodeau

A compact set of synthetic faces is generated that resemble individuals of interest under the capture conditions relevant to the OD.

3D Reconstruction Clustering +2

Evaluation of trackers for Pan-Tilt-Zoom Scenarios

no code implementations12 Nov 2017 Yucao Tang, Guillaume-Alexandre Bilodeau

Compared to tracking with a still camera, the images captured with a PTZ camera are highly dynamic in nature because the camera can perform large motion resulting in quickly changing capture conditions.

Position

Robust Face Tracking using Multiple Appearance Models and Graph Relational Learning

1 code implementation29 Jun 2017 Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger

This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios.

Relational Reasoning

Discriminative conditional restricted Boltzmann machine for discrete choice and latent variable modelling

no code implementations1 Jun 2017 Melvin Wong, Bilal Farooq, Guillaume-Alexandre Bilodeau

Our findings show that through non-parametric statistical tests, we can extract useful latent information on the behaviour of latent constructs through machine learning methods and present strong and significant influence on the choice process.

Tracking using Numerous Anchor points

2 code implementations7 Feb 2017 Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger

In this paper, an online adaptive model-free tracker is proposed to track single objects in video sequences to deal with real-world tracking challenges like low-resolution, object deformation, occlusion and motion blur.

Object Object Localization +1

SPiKeS: Superpixel-Keypoints Structure for Robust Visual Tracking

no code implementations23 Oct 2016 François-Xavier Derue, Guillaume-Alexandre Bilodeau, Robert Bergevin

In visual tracking, part-based trackers are attractive since they are robust against occlusion and deformation.

Superpixels Visual Tracking

Reproducible Evaluation of Pan-Tilt-Zoom Tracking

no code implementations18 May 2015 Gengjie Chen, Pierre-Luc St-Charles, Wassim Bouachir, Thomas Joeisseint, Guillaume-Alexandre Bilodeau, Robert Bergevin

Tracking with a Pan-Tilt-Zoom (PTZ) camera has been a research topic in computer vision for many years.

Automatic Image Registration in Infrared-Visible Videos using Polygon Vertices

no code implementations17 Mar 2014 Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger

To achieve a global affine transformation that maximises the overlapping of infrared and visible foreground pixels, the matched keypoints of each local shape polygon are stored temporally in a buffer for a few number of frames.

Image Registration

Cannot find the paper you are looking for? You can Submit a new open access paper.